DC Field | Value | Language |
---|---|---|
dc.contributor.author | Heting Gao | ko |
dc.contributor.author | Mark Hasegawa-Johnson | ko |
dc.contributor.author | Yoo, Chang-Dong | ko |
dc.date.accessioned | 2024-09-28T04:00:14Z | - |
dc.date.available | 2024-09-28T04:00:14Z | - |
dc.date.created | 2024-09-28 | - |
dc.date.issued | 2024-04 | - |
dc.identifier.citation | 2024 IEEE International Conference on Acoustics, Speech and Signal Processing | - |
dc.identifier.uri | http://hdl.handle.net/10203/323310 | - |
dc.description.abstract | Most phoneme transcripts are generated using forced alignment: typically a grapheme-to-phoneme transducer (G2P) is applied to text sequences to generate candidate phoneme transcripts, which are then time-aligned to the waveform using an acoustic model. This paper demonstrates, for the first time, simultaneous optimization of the G2P, the acoustic model, and the acoustic alignment to a corpus. To this end, we propose G2PU, a joint CTC-attention model consisting of an encoder-decoder G2P network and an encoder-CTC unit-to-phoneme (U2P) network, where the units are extracted from speech. We demonstrate that the G2P and U2P, operating in parallel, produce lower phone error rates than those of state-of-the-art open-source G2P and forced alignment systems. Furthermore, although the G2P and U2P are trained using parallel speech and text, their synergy can be generalized to text-only test corpora if we also train a grapheme-to-unit (G2U) network that generates speech units from text in the absence of parallel speech. Our G2PU model is trained using phoneme transcripts generated by a teacher G2P tool. Our experiments on Chinese and Japanese show that G2PU reduces phoneme error rate by 7% to 29% relative compared to its teacher. Finally, we include case studies to provide insights into the system’s workings. | - |
dc.language | English | - |
dc.publisher | 2024 IEEE International Conference on Acoustics, Speech and Signal Processing | - |
dc.title | G2PU: Grapheme-To-Phoneme Transducer with Speech Units | - |
dc.title.alternative | G2PU: Grapheme-To-Phoneme Transducer with Speech Units | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 2024 IEEE International Conference on Acoustics, Speech and Signal Processing | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | COEX | - |
dc.contributor.localauthor | Yoo, Chang-Dong | - |
dc.contributor.nonIdAuthor | Heting Gao | - |
dc.contributor.nonIdAuthor | Mark Hasegawa-Johnson | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.